© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27058
    Prev
    Next
    INDEX
    Explanations

    statements indicating the state or condition of subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Inflate
    -0.07
    наÑĢод
    -0.07
    ghost
    -0.07
    YST
    -0.07
     mie
    -0.07
    vat
    -0.07
    nty
    -0.06
    .sponge
    -0.06
    utilus
    -0.06
    kol
    -0.06
    POSITIVE LOGITS
     wide
    0.07
    -wide
    0.07
    ãĥ¼ãĥ©
    0.07
    wide
    0.06
     binary
    0.06
    ç·Ĵ
    0.06
     |-
    0.06
    -binary
    0.06
    ozy
    0.06
    zin
    0.06
    Activations Density 0.026%

    No Known Activations